---
title: "List Inference History"
method: GET
path: "/v1/inferences"
tags: ["inference-history"]
---

# List Inference History

`GET /v1/inferences`

## Request

- Base URL: `https://api.fastino.ai`
- URL: `https://api.fastino.ai/v1/inferences`
- Auth: one of:
  - API key in header `X-API-Key`
  - HTTP bearer
- TypeScript: <https://skmtc.dev/fastino-ai/apis/pioneer-inference-api/docs/v1/inferences/get.ts> (a function with typed inputs; its response is checked against the schema)

List inference history for the authenticated user.

Returns all inference records across all model types (NER, classification,
JSON extraction, decoder) sorted by most recent first.

## Query parameters

- `limit` integer: Maximum records to return
- `offset` integer: Number of records to skip
- `model_id` string, nullable: Filter by model ID
- `task` string, nullable: Filter by task type
- `project_id` string, nullable: Filter by project ID
- `training_job_id` string, nullable: Filter by training job ID
- `latency_min` number, nullable: Minimum latency in ms (must be >= 0).
- `latency_max` number, nullable: Maximum latency in ms (must be >= 0).
- `llmaj_score_min` number, nullable: Minimum LLM-as-Judge score in [0.0, 1.0].
- `llmaj_score_max` number, nullable: Maximum LLM-as-Judge score in [0.0, 1.0].
- `since` string, nullable: Inclusive lower bound on created_at (ISO 8601, UTC).
- `until` string, nullable: Exclusive upper bound on created_at (ISO 8601, UTC).

## Response `200`

Successful Response

- InferenceListResponse: Response for listing inference history.
  - `inferences` InferenceRecord[], required: List of inference records
    - `base_model` string, nullable: HuggingFace base model ID
    - `cache_read_tokens` integer, nullable: Input tokens served from the provider prompt cache (cache hit).
    - `cache_write_tokens` integer, nullable: Input tokens written into the provider prompt cache (cache creation). Zero for providers that bill writes as plain input.
    - `created_at` string, date-time, required: When the inference was made
    - `error_message` string, nullable: Error detail when status is failed
    - `error_type` string, nullable: Failure category when status is failed (validation, timeout, model_not_ready, model_not_found, model_not_supported, capacity_exhausted, internal)
    - `human_corrected_output` unknown
    - `human_feedback_at` string, date-time, nullable: When human feedback was submitted
    - `human_feedback_by` string, nullable: User ID of the member who submitted the current human feedback
    - `human_feedback_notes` string, nullable: Optional reviewer notes
    - `human_verdict` string, nullable: Human reviewer verdict (correct/incorrect)
    - `id` string, required: Unique inference ID
    - `input` string, required: Input text
    - `input_tokens` integer, nullable: Non-cached input/prompt tokens, sourced from the metered requests row. None when no billing row was recorded.
    - `latency_ms` integer, nullable: End-to-end latency in milliseconds
    - `llmaj_judged_at` string, date-time, nullable: Timestamp when LLMAJ judgment was recorded; None until judged.
    - `llmaj_reasoning` string, nullable: LLMAJ judge reasoning/explanation; None until judged.
    - `llmaj_score` number, nullable: Historical LLMAJ confidence score in [0.0, 1.0].
    - `llmaj_verdict` 'pass' | 'fail' | 'uncertain', nullable: Historical LLMAJ verdict ('pass', 'fail', or 'uncertain').
    - `metadata` object, nullable: Extensible metadata (e.g. LLM judge results)
    - `model_id` string, required: Model ID used for inference
    - `model_name` string, nullable: Human-readable model name
    - `output` unknown
    - `output_tokens` integer, nullable: Output/completion tokens, sourced from the metered requests row.
    - `project_id` string, nullable: Project ID the model belongs to
    - `provider` string, nullable: Inference provider (aws, modal, etc.). Rows predating a provider removal carry an 'archived_<provider>' label.
    - `source` string: Source of the request (api or ui)
    - `status` string: Inference status: success or failed
    - `task` string, nullable: Task type (legacy; may be NULL for new inferences)
    - `tokens` integer, nullable: Token count
    - `training_job_id` string, nullable: Training job UUID that produced the model
    - `ttft_ms` integer, nullable: Streaming time to first visible output chunk in milliseconds; null for non-streaming calls and streams with no visible payload.
    - `user_id` string, required: User who made the inference
  - `limit` integer, required: Page size limit
  - `offset` integer, required: Current offset
  - `total` integer, required: Total count of inferences matching filters

## Other responses

- `422`: Validation Error
- `503`: Inference history dependency is temporarily unavailable.

## Changes

- **2026-10-15** `ef285860f952`: 1 info
  - added the optional property `inferences/items/human_feedback_by` to the response with the `200` status
- **2026-10-12** `43d7e06a824b`: 1 warning
  - for the `query` request parameter `offset`, the max was set to `10000000.00`
- **2026-09-28** `54da122a2879`: 1 info
  - api operation id `list_inference_history_inferences_get` removed and replaced with `list_inference_history_v1_inferences_get`
- **2026-09-23** `620970c6f5f2`: 1 info
  - endpoint added

[Operation history](https://skmtc.dev/fastino-ai/apis/pioneer-inference-api/changes/v1/inferences/get.md)

---

[API](https://skmtc.dev/fastino-ai/apis/pioneer-inference-api.md) - [All operations](https://skmtc.dev/fastino-ai/apis/pioneer-inference-api/llms.txt) - [OpenAPI document](https://skmtc.dev/fastino-ai/apis/pioneer-inference-api/revisions/81465e18c1d2?raw)